Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

2x speedup with IBM foundation stack #1615

Closed
casper-hansen opened this issue Nov 9, 2023 · 2 comments
Closed

2x speedup with IBM foundation stack #1615

casper-hansen opened this issue Nov 9, 2023 · 2 comments
Labels
performance Performance-related issues

Comments

@casper-hansen
Copy link
Contributor

They rewrite Llama model definition to be compatible with torch.compile. Completely open source.

https://github.com/foundation-model-stack/foundation-model-stack
@WoosukKwon WoosukKwon added the performance Performance-related issues label Nov 9, 2023
@WoosukKwon
Copy link
Collaborator

Hi @casper-hansen, thanks for bringing it up. Indeed, we are actively investigating torch.compile support.

@hmellor
Copy link
Collaborator

hmellor commented Mar 13, 2024

Closing because torch.compile is on the roadmap #2681

@hmellor hmellor closed this as completed Mar 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
performance Performance-related issues
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@hmellor @casper-hansen @WoosukKwon